How to Use the Brightcove MCP in LangChain

Q: Can I trace Brightcove tool execution in LangSmith?

Yes, every call to getvideo or updatevideo shows up as a distinct tool run in your LangSmith dashboard. You can inspect the exact inputs, outputs, and execution latency of your Brightcove operations inside your active chains.

Q: How do I pass Brightcove tools to a LangChain agent?

You initialize the MCP adapter, call gettools(), and feed those tools directly into your LangChain createreactagent function. This exposes tools like createplaylist and deletevideo to your agent without manual schema definition.

Run multi-step LangChain chains that manage playlists and query video metadata directly from your Brightcove account.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Brightcove MCP to LangChain

Create your Vinkius account to connect Brightcove to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Brightcove with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Brightcove video queries directly in LangChain chains

The `list_videos` tool fetches your entire Brightcove catalog directly into your active LangChain chain. Your agent inspects this list, filters by specific tags, and feeds the filtered video IDs directly into the next step of your pipeline. LangSmith traces the exact latency of this data fetch, letting you debug how your agent processes video payloads. You don't write custom wrapper code; you just pass the raw MCP Server schema to your agent executor.

Automate playlist curation based on video counts

The `get_video_count` tool gives your chain the exact size of your library before you structure new playlists. Your agent uses this metric to decide whether to split videos across multiple groups or build a single collection. Once the agent calculates the grouping, it calls `create_playlist` to build the structure in your Brightcove account. The output of the count tool flows directly into the playlist creation tool as a variable in your LangGraph run.

Reorganize video folders dynamically

The `list_folders` tool exposes your entire Brightcove folder hierarchy to your LangChain agent. When you need to audit assets, the agent reads this folder list and compares it with your current project requirements. The agent then runs `get_folder_videos` to pull assets from specific directories. This execution pattern lets your chain identify misplaced videos and group them without manual browser work.

Setup guide

Set up Brightcove MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Brightcove tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "brightcove-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Brightcove transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Brightcove. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Brightcove now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Brightcove MCP in LangChain

Your LangChain agent handles rate limits through the underlying Vinkius MCP Server connection. If Brightcove throttles a request during a `list_videos` call, the adapter manages the backoff before passing the clean JSON output back to your chain.

Yes, every call to `get_video` or `update_video` shows up as a distinct tool run in your LangSmith dashboard. You can inspect the exact inputs, outputs, and execution latency of your Brightcove operations inside your active chains.

You initialize the MCP adapter, call `get_tools()`, and feed those tools directly into your LangChain `create_react_agent` function. This exposes tools like `create_playlist` and `delete_video` to your agent without manual schema definition.

It works natively. You can store the video metadata retrieved from `get_playlist` in your graph's state, allowing subsequent nodes to reference the same Brightcove assets.

Vinkius runs the server in an isolated V8 sandbox, meaning your Brightcove API tokens and folder lists never persist on disk. Only the active JSON payloads for tools like `list_playlists` pass through the ephemeral runtime.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript